Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    statements involving assumptions or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isos
    -0.15
    ense
    -0.15
    urm
    -0.15
    ibal
    -0.15
    ãģ¾ãĤĭ
    -0.14
    lh
    -0.14
    NECT
    -0.14
    nown
    -0.14
     pornstar
    -0.14
    datagrid
    -0.14
    POSITIVE LOGITS
     assumed
    0.22
     assumption
    0.21
     assume
    0.19
    assume
    0.18
     assumptions
    0.17
     premise
    0.17
     Assumes
    0.17
     assumes
    0.17
    etty
    0.17
    inea
    0.17
    Act Density 0.116%

    No Known Activations